Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    transformation

    np_max-act · gemini-2.0-flash

    This neuron activates on Polish words (i.e. tokens from Polish text).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     estudio
    -0.06
    iba
    -0.06
    twig
    -0.06
     Cardinal
    -0.06
    icode
    -0.06
    vette
    -0.06
    otypical
    -0.06
    fleet
    -0.06
     Rim
    -0.06
     فتح
    -0.06
    POSITIVE LOGITS
    &p
    0.06
     Chủ
    0.06
    ект
    0.06
     академ
    0.06
     výši
    0.06
    Adding
    0.06
    ",@"
    0.06
    ,o
    0.06
     біль
    0.06
     Tre
    0.06
    Act Density 0.210%

    No Known Activations